# Bounding the smallest singular value of a random matrix without concentration

@article{Koltchinskii2013BoundingTS, title={Bounding the smallest singular value of a random matrix without concentration}, author={Vladimir Koltchinskii and Shahar Mendelson}, journal={arXiv: Probability}, year={2013} }

Given $X$ a random vector in ${\mathbb{R}}^n$, set $X_1,...,X_N$ to be independent copies of $X$ and let $\Gamma=\frac{1}{\sqrt{N}}\sum_{i=1}^N e_i$ be the matrix whose rows are $\frac{X_1}{\sqrt{N}},\dots, \frac{X_N}{\sqrt{N}}$.
We obtain sharp probabilistic lower bounds on the smallest singular value $\lambda_{\min}(\Gamma)$ in a rather general situation, and in particular, under the assumption that $X$ is an isotropic random vector for which $\sup_{t\in S^{n-1}}{\mathbb{E}}| |^{2+\eta} \leq…

## 144 Citations

Sharp lower bounds on the least singular value of a random matrix without the fourth moment condition

- Mathematics
- 2015

We obtain non-asymptotic lower bounds on the least singular value of ${\mathbf X}_{pn}^\top/\sqrt{n}$, where ${\mathbf X}_{pn}$ is a $p\times n$ random matrix whose columns are independent copies of…

Sample covariance matrices of heavy-tailed distributions

- Mathematics
- 2016

Let $p>2$, $B\geq 1$, $N\geq n$ and let $X$ be a centered $n$-dimensional random vector with the identity covariance matrix such that $\sup\limits_{a\in S^{n-1}}{\mathrm E}|\langle X,a\rangle|^p\leq…

The limit of the smallest singular value of random matrices with i.i.d. entries

- Mathematics
- 2014

Let $\{a_{ij}\}$ $(1\le i,j<\infty)$ be i.i.d. real valued random variables with zero mean and unit variance and let an integer sequence $(N_m)_{m=1}^\infty$ satisfy $m/N_m\longrightarrow z$ for some…

On the interval of fluctuation of the singular values of random matrices

- Computer Science, MathematicsArXiv
- 2015

It is proved that with high probability A/A has the Restricted Isometry Property (RIP) provided that Euclidean norms $|X_i|$ are concentrated around $\sqrt{n}$.

The smallest singular value of random rectangular matrices with no moment assumptions on entries

- Mathematics
- 2014

Let δ > 1 and β > 0 be some real numbers. We prove that there are positive u, v, N0 depending only on β and δ with the following property: for any N,n such that N ≥ max(N0, δn), any N × n random…

Regularization and the small-ball method II: complexity dependent error rates

- Mathematics, Computer ScienceJ. Mach. Learn. Res.
- 2017

The general estimation bound to various choices of $\Psi$ is applied, for example, the $\ell_p$ and $S-p$-norms (for $p\geq1$), weak-$\ell-p$, atomic norms, max-norm and SLOPE.

The smallest singular value of a shifted d-regular random square matrix

- MathematicsProbability Theory and Related Fields
- 2018

We derive a lower bound on the smallest singular value of a random d-regular matrix, that is, the adjacency matrix of a random d-regular directed graph. Specifically, let $$C_1<d< c n/\log ^2…

On delocalization of eigenvectors of random non-Hermitian matrices

- Mathematics
- 2018

We study delocalization of null vectors and eigenvectors of random matrices with i.i.d entries. Let A be an $$n\times n$$ n × n random matrix with i.i.d real subgaussian entries of zero mean and unit…

A convex program for bilinear inversion of sparse vectors

- Mathematics, Computer ScienceNeurIPS
- 2018

The introduced $\ell_1$-BranchHull, which is a convex program posed in the natural parameter space and does not require an approximate solution or initialization in order to be stated or solved, and an ADMM implementation of these variants are provided.

Performance of empirical risk minimization in linear aggregation

- Mathematics
- 2016

We study conditions under which, given a dictionary $F=\{f_1,\ldots ,f_M\}$ and an i.i.d. sample $(X_i,Y_i)_{i=1}^N$, the empirical minimizer in $\operatorname {span}(F)$ relative to the squared…

## References

SHOWING 1-10 OF 24 REFERENCES

Sharp bounds on the rate of convergence of the empirical covariance matrix

- Mathematics
- 2010

Let $X_1,..., X_N\in\R^n$ be independent centered random vectors with log-concave distribution and with the identity as covariance matrix. We show that with overwhelming probability at least $1 - 3…

The limit of the smallest singular value of random matrices with i.i.d. entries

- Mathematics
- 2014

Let $\{a_{ij}\}$ $(1\le i,j<\infty)$ be i.i.d. real valued random variables with zero mean and unit variance and let an integer sequence $(N_m)_{m=1}^\infty$ satisfy $m/N_m\longrightarrow z$ for some…

On the interval of fluctuation of the singular values of random matrices

- Computer Science, MathematicsArXiv
- 2015

It is proved that with high probability A/A has the Restricted Isometry Property (RIP) provided that Euclidean norms $|X_i|$ are concentrated around $\sqrt{n}$.

The smallest singular value of random rectangular matrices with no moment assumptions on entries

- Mathematics
- 2014

Let δ > 1 and β > 0 be some real numbers. We prove that there are positive u, v, N0 depending only on β and δ with the following property: for any N,n such that N ≥ max(N0, δn), any N × n random…

Quantitative estimates of the convergence of the empirical covariance matrix in log-concave ensembles

- Mathematics
- 2009

Let K be an isotropic convex body in Rn. Given e > 0, how many independent points Xi uniformly distributed on K are neededfor the empirical covariance matrix to approximate the identity up to e with…

Concentration Inequalities - A Nonasymptotic Theory of Independence

- Mathematics, Computer ScienceConcentration Inequalities
- 2013

Deep connections with isoperimetric problems are revealed whilst special attention is paid to applications to the supremum of empirical processes.

Covariance estimation for distributions with 2+ε moments

- Mathematics
- 2013

We study the minimal sample size N=N(n) that suffices to estimate the covariance matrix of an n-dimensional distribution by the sample covariance matrix in the operator norm, with an arbitrary fixed…

On the singular values of random matrices

- Mathematics
- 2014

We present an approach that allows one to bound the largest and smallest singular values of an N × n random matrix with iid rows, distributed according to a measure on Rn that is supported in a…

Decoupling: From Dependence to Independence

- Mathematics
- 1998

1 Sums of Independent Random Variables.- 1.1 Levy-Type Maximal Inequalities.- 1.2 Hoffmann-J?rgensen Type Inequalities.- 1.3 The Khinchin-Kahane Inequalities.- 1.4 Moment Bounds.- 1.4.1 Maxima.-…

The lower tail of random quadratic forms with applications to ordinary least squares

- Mathematics, Computer ScienceArXiv
- 2013

This paper proves that the “lower tail” of such a matrix is sub-Gaussian under a simple fourth moment assumption on the one-dimensional marginals of the random vectors, and obtains a nearly optimal finite-sample result for the ordinary least squares estimator under random design.